RU2760243C2 - System and method for improving request for creating distributed group of resources based on time delay - Google Patents

Abstract

FIELD: computer technology.

SUBSTANCE: system for improving a request for creating a distributed resource group based on a time delay is disclosed, containing: network nodes logically separated based on a set of time delay indexes {Ti} to obtain a group of containers consisting of a set of containers having a nested relationship, while each container contains a control node used to organize nodes, maintain neighborhood and service requests in the container; each time delay index Ti corresponds to a layer of a Ci-level container without intersection and with full coverage, wherein Ci-level containers have a nested relationship with each other, that is, a set of Ci-level containers make up a Ci+1-level container, while Ti<Ti+1, 1≤i≤I-1, where I is a number of layers of nested containers, and Ti is an actual index of a request time delay; the control topology of the system for improving a request for creating a distributed group of resources based on a time delay is a tree structure, and a root node is a control node for a Ci-level container; a local request node, which is accessed through any request, is designated as LQNj, and it forms a section of a distributed group of resources together with a Ci-level container containing a local request node (LQNj) and neighboring container elements in order to satisfy request requirements that the time delay index {Ti} must be less than any specified upper limit of the time delay Ts.

EFFECT: providing a system for improving a request for creating a distributed group of resources based on the time delay.

12 cl, 1 dwg

Description

This application claims the priority of PRC Patent Application No. 201710841537.4, filed September 18, 2017, entitled "Query Enhancement System and Method for Constructing Elastic Field Based on Time Delay," the contents of which are incorporated herein by reference in their entirety.

The technical field to which the invention relates

The present invention relates to the field of network technology and communication technology over a network, and in particular relates to a system and method for enhancing a request for creating an allocable resource group based on a time delay.

Background of the invention

In the prior art, a distributed query includes: a Range query, an aggregate query, a Skyline query, and a Top-k query (top k items). Moreover, a Range query means searching for all resources with one or many attribute values that are in a certain continuous interval, for example, an attribute identification can be obtained through a position-sensitive hashing algorithm based on Chord, and a mapping between one attribute can be applied. and multiple attributes in space filling curve (SFC) technology; an aggregation request refers to a request for some aggregation information, such as the number, sum, maximum value, and average value, of some attributes in a resource group; and a Skyline query means selecting one subset from a given set S, in which any point in the subset is not controlled by other points in S, and a controllable relationship of any two points of type "p is greater than q" means that p is greater than q by at least some dimension and that p does not obey q in other dimensions.

In a typical distributed query application, the mapping system of the mapping relationship between name and address is a mandatory reference in information-oriented network (ICN) communications, and the characteristics of the mapping system directly affect the overall performance of the information-oriented network (ICN). Through the Information-Oriented Network (ICN) naming mechanism, each entity in the network is assigned a unique entity identifier (EUID), independent of position and self-validation features such as name, and through dynamic linking between EUIDs and EUID network addresses (NA), communication is realized between actors in an information-oriented network (ICN). Name translation is primarily intended to establish and maintain a mapping relationship between the content name published by the content provider and the network address (s), and to find the correct content provider and its network address by extracting the content name. However, prior art solutions have the following problems:

1) although the content space is nested or stacked in layers by a container or structured technique according to the characteristics of the network, the existing partitioning method does not depend on the response time and the requirements of the system application, while the independence of the structural performance characteristics obviously cannot directly satisfy the time delay requirements ;

2) In an environment that has a higher requirement for mobility and security, a method for applying elastic scalable query according to the response time or performance requirements cannot be provided, and the search efficiency and accuracy cannot be ensured while the resource utilization rate is increased.

In addition, in current distributed query applications, the query response time is usually related to the scale of the node, the size of the query chunk, and the number of resource attributes in the query (i.e., the spatial size), however, query results cannot be returned within a fixed time delay. In order to overcome the above problems, it is necessary to provide a system and method for improving the query to create an allocable resource group based on time lag in order to satisfy the request processing requirement of returning query results within a predetermined low time lag in some use cases.

Thus, the technical result to which the claimed invention is directed is to provide a request enhancement system for creating an allocated resource group based on a time delay, with the help of which the problems of organizing distribution and request are effectively eliminated, preferably applications with the requirements of a given low time delay are handled. in an information-oriented network (ICN) and a distributed nearest request is implemented taking into account the positional relationship from near to far.

The essence of the invention

The object of the present invention is as follows: in order to eliminate the above problems existing in the existing system and method for improving the request, the present invention proposes a request enhancement system for creating an allocated resource group based on a time delay, by which the problems of organizing distribution and request are effectively eliminated, preferably processing applications requiring a given low latency in an information-oriented network (ICN), and implementing a distributed nearest request based on near-to-far positional relationship.

To achieve the above object, the present invention proposes a request enhancement system for creating an allocable resource group based on a time delay, comprising: the network nodes are logically separated to obtain a container group consisting of a plurality of containers; moreover, the plurality of containers have a nested relationship, that is, the plurality of containers constitute a group of containers, and each container further comprises: a control node used to organize nodes, maintain neighborhood and serve requests in the container; moreover, logical separation refers to the reallocation of a set of physical nodes according to a predetermined container rule to form a set of logical nodes, whereby nodes that are not in the same physical volume can also form a relationship in the form of a neighborhood; organization of nodes refers to the structured management of nodes in a container to form a logical topological structure; Neighborhood maintenance refers to maintaining a direct connection state in a logical topological structure; and servicing requests refers to retrieving the database after receiving the request to return the requested content.

The query enhancement system for creating an allocated resource group based on time delay, in particular, provides the following: based on a set of time delay indices {Ti}, the network nodes are logically separated, with each time delay index Ti corresponding to a container layer of the Ci level without intersection and with full coverage , containers of level Ci have a nested relationship with each other, that is, many containers of level Ci constitute a container of level Ci + 1, where Ti <Ti + 1, 1≤i≤I-1, where I is the number of layers of nested containers, and Ti is is the actual index of the time delay for the request.

The control topology of the request enhancement system for creating an allocable resource group based on the time delay is a tree structure, and the root node is a CI-level container control node; any local request node that is accessed through a request is denoted as LQNj and forms a portion of the resource group to be allocated together with a Ci-level container containing the local request node (LQNj) and neighboring container elements to satisfy the request's requirement that that the set of time delay indices {Ti} should be less than any given upper limit of the time delay Ts.

The query requirement that the set of time delay indices {Ti} must be less than any given upper limit of the time delay Ts, specifically provides for the following:

a) when Ts <T1 and i = 1, a request in the LQNj receiving the request reference, the C1 container containing the LQNj, and the neighboring elements of the container;

b) when Ti≤Ts <Ti + 1, querying in the Ci level container containing LQNj and its neighbors;

c) when Ts≥TI, i = I, request in the CI container containing LQNj.

Based on a request enhancement system for creating an allocated resource group based on a time delay, the present invention also discloses a method for improving a request for creating an allocated resource group based on a time delay, including: subjecting network nodes to logical separation without intersection and with full coverage on each layer to obtain a group of containers consisting of a plurality of containers, the plurality of containers having a nested relationship, and, accordingly, executing a flow of requests without requiring a predetermined low latency and a flow of nearby requests with requirements of a predetermined low latency; moreover

the flow of requests without the requirement of a predetermined low latency is realized by using the existing request technology;

The flow of requests requiring a predetermined low latency time adopts the distributed nearest request method for the nearest request, whereby the fact that the actual request time lag index Ti is less than the requirements of a certain upper limit of the time delay Ts, in particular, provides the following:

step 1) when Ti <Ts, receiving by a certain local node a request (LQNj) a request request for a given low latency requirement directed to a specific subject unique identifier (ID), where Ti is the actual query latency index and Ts is is the upper limit of the time delay;

step 2), when i = 1, evaluating whether Ts <T1 is satisfied, and if Ts <T1, go to the next step; if Ts is greater than or equal to T1, go directly to step 4);

step 3), when Ts <T1 and i = 1, requesting the LQNj receiving the request access, the C1 container containing the LQNj, and the neighboring elements of the container; in case of a successful request for the network address (s) corresponding to the identifier, direct return of the query results; in case of unsuccessful request for the network address corresponding to the identifier, return a negative result of the request;

step 4), for any condition satisfying 1≤i≤I-1, check if Ti≤Ts <Ti + 1: if Ti≤Ts <Ti + 1 is satisfied, go to the next step if Ti≤Ts < Ti + 1 is not satisfied, go directly to step 7);

step 5) when Ti≤Ts <Ti + 1, forwarding the request to the request node of the Ci level container containing LQNj and designating the container as Cik, and performing a preliminary query in Cik and its neighbor list {Cim}; in case of a successful request for the network address (s) corresponding to the identifier, go to the next stage; in case of unsuccessful request for the network address corresponding to the identifier, return a negative result of the request;

step 6) requesting Cik and its neighbor list {Cim}; in the case of a successful request for the network address (network addresses) corresponding to the identifier, direct return of the query results, in the case of an unsuccessful request for the network address corresponding to the identifier, return a negative result of the request;

step 7), executing the preliminary request in the container of the CI level containing the LQNj; in case of a successful request for the network address (s) corresponding to the identifier, go to the next stage; in case of unsuccessful request for the network address corresponding to the identifier, go directly to step 9);

step 8), requesting in the container of the CI level containing the LQNj; in case of a successful request for the network address (s) corresponding to the identifier, direct return of the query results; in case of unsuccessful request for the network address corresponding to the identifier, go to the next stage;

step 9) requesting the neighbor list {CIm} of the CI layer container containing the LQNj through inter-domain exchange; in case of successful request of the network address (s) corresponding to the identifier in a certain container of the CI level, designating the container as CIp and proceeding to the next stage; in case of unsuccessful request for the network address corresponding to the identifier, return a negative result of the request; and

Step 10), forwarding the CIp request and requesting the CIp; in case of a successful request for the network address (s) corresponding to the identifier, direct return of the query results; in case of unsuccessful request for the network address corresponding to the identifier, return a negative result of the request;

preferably in step 3) the query is executed in the LQNj receiving the request reference, the C1 container containing the LQNj, and the local hash table (HT) in the neighbors;

preferably in step 5) the query is performed on a Bloom filter (BF) in Cik and its neighbor list {Cim};

preferably in step 6) the query is performed on a distributed hash table (DHT) in Cik and its neighbor list {Cim};

preferably in step 7) the preliminary request is performed in a Bloom filter (BF) in a container of the CI layer containing LQNj;

preferably in step 8) the query is performed on a distributed hash table (DHT) in a CI-level container containing LQNj;

preferably in step 9) the query is performed in a Bloom filter (BF) in the neighbor list {CIm} of the CI layer container containing LQNj; and

preferably the query is performed on a distributed hash table (DHT) in the CIp.

In the above technical solution, regarding the flow of nearest requests with the requirements of a given low latency, in order to save maintenance costs, the list of neighbors {C1m} C1k can be reduced to a C1 level container with no neighbors, and the specific flow of requests includes the following:

step 1) when Ti <Ts, receiving by a certain local node a request (LQNj) a request requesting a given low time delay request directed to a certain unique identifier (ID) of the subject, where Ti is the actual time delay index of the request, and Ts is is the upper limit of the time delay;

step 2) when i = 1, judging whether Ts <T1 is satisfied: if Ts <T1, go to the next step; if Ts is greater than or equal to T1, go directly to step 4);

step 3), when Ts <T1 and i = 1, requesting the LQNj receiving the request reference, the C1 container containing the LQNj and its neighbors; in case of a successful request for the network address (s) corresponding to the identifier, direct return of the query results; in case of unsuccessful request for the network address corresponding to the identifier, return a negative result of the request;

step 4), for any condition satisfying 1≤i≤I-1, check if Ti≤Ts <Ti + 1: if Ti≤Ts <Ti + 1 is satisfied, go to the next step if Ti≤Ts < Ti + 1 is not satisfied, go directly to step 7);

step 5) when Ti≤Ts <Ti + 1, forwarding the request to the request node of the Ci level container containing LQNj and designating the container as Cik, and performing a preliminary query in Cik and its neighbor list {Cim}; in case of a successful request for the network address (s) corresponding to the identifier, go to the next stage; in case of unsuccessful request for the network address corresponding to the identifier, return a negative result of the request;

step 6) requesting Cik and its neighbor list {Cim}; in the case of a successful request for the network address (network addresses) corresponding to the identifier, direct return of the query results, in the case of an unsuccessful request for the network address corresponding to the identifier, return a negative result of the request;

step 7), executing the preliminary request in the container of the CI level containing the LQNj; in case of a successful request for the network address (s) corresponding to the identifier, go to the next stage; in case of unsuccessful request for the network address corresponding to the identifier, go directly to step 9); and

step 8), requesting in the container of the CI level containing the LQNj; in case of a successful request for the network address (s) corresponding to the identifier, direct return of the query results; in case of unsuccessful request for the network address corresponding to the identifier, go to the next stage;

preferably in step 5) the query is performed on a Bloom filter (BF) in Cik and its neighbor list {Cim};

preferably in step 6) the query is performed on a distributed hash table (DHT) in Cik and its neighbor list {Cim};

preferably in step 7) the preliminary request is performed in a Bloom filter (BF) in a container of the CI layer containing LQNj;

preferably in step 8) the query is performed on a distributed hash table (DHT) in a CI layer container containing LQNj.

The present invention has the following advantages: it is directed to various time-sensitive applications providing low latency and high reliability, the present invention discloses a system and method for enhancing a request for creating an allocated resource group based on a time delay, and thereby satisfying processing requirements call, which consists in returning the results of a query within a specified low time delay. By distributed closest request considering the positional relationship from near to far and by processing according to the priority of low latency applications, the total request time can be significantly reduced.

Brief description of graphic materials

FIG. 1 is a block diagram of a request enhancement system for creating an allocable resource group based on a time delay in accordance with the present invention.

Detailed Description of Embodiments

As shown in FIG. 1, the present invention proposes a request enhancement system for creating an allocable resource group based on a time delay, comprising: network nodes are logically separated to obtain a container group consisting of a plurality of containers; moreover, the plurality of containers have a nested relationship, that is, the plurality of containers constitute a group of containers, and each container further comprises: a control node used to organize nodes, maintain neighborhood and serve requests in the container; moreover, logical separation refers to the reallocation of a set of physical nodes according to a predetermined container rule to form a set of logical nodes, whereby nodes that are not in the same physical volume can also form a relationship in the form of a neighborhood; organization of nodes refers to the structured management of nodes in a container to form a logical topological structure; Neighborhood maintenance refers to maintaining a direct connection state in a logical topological structure; and servicing requests refers to retrieving the database after receiving the request to return the requested content.

The query enhancement system for creating an allocated resource group based on time delay, in particular, provides the following: based on a set of time delay indices {Ti}, the network nodes are logically separated, with each time delay index Ti corresponding to a container layer of the Ci level without intersection and with full coverage , containers of level Ci have a nested relationship with each other, that is, many containers of level Ci constitute a container of level Ci + 1, where Ti <Ti + 1, 1≤i≤I-1, where I is the number of layers of nested containers, and Ti is is the actual index of the time delay for the request.

The control topology of the request enhancement system for creating an allocable resource group based on the time delay is a tree structure, and the root node is a CI-level container control node; any local request node that is accessed through a request is denoted as LQNj and forms a portion of the resource group to be allocated together with a Ci-level container containing the local request node (LQNj) and neighboring container elements to satisfy the request's requirement that that the time delay index {Ti} should be less than any predetermined upper limit of the time delay Ts.

The query requirement that the set of time delay indices {Ti} must be less than any given upper limit of the time delay Ts, specifically provides for the following:

a) when Ts <T1 and i = 1, a request in the LQNj receiving the request reference, the C1 container containing the LQNj, and the neighboring elements of the container;

b) when Ti≤Ts <Ti + 1, querying in the Ci level container containing LQNj and its neighbors; and

c) when Ts≥TI, i = I, request in the CI container containing LQNj.

Based on a request enhancement system for creating an allocated resource group based on a time delay, the present invention also discloses a method for improving a request for creating an allocated resource group based on a time delay, including: subjecting network nodes to logical separation without intersection and with full coverage on each layer to obtain a group of containers consisting of a plurality of containers, the plurality of containers having a nested relationship, and, accordingly, executing a flow of requests without requiring a predetermined low latency and a flow of nearby requests with requirements of a predetermined low latency; moreover

the flow of requests without the requirement of a predetermined low latency is realized by using the existing request technology;

The flow of requests with the requirements of a given low time delay applies the distributed nearest request method for the nearest request, whereby the fact that the actual time delay index of the request Ti is less than the requirements of a certain upper limit of the time delay Ts, in particular, provides the following:

step 1) when Ti <Ts, receiving by a certain local node a request (LQNj) a request request for a given low latency requirement directed to a specific subject unique identifier (ID), where Ti is the actual query latency index and Ts is is the upper limit of the time delay;

step 2), when i = 1, evaluating whether Ts <T1 is satisfied, and if Ts <T1, go to the next step; if Ts is greater than or equal to T1, go directly to step 4);

step 3), when Ts <T1 and i = 1, requesting the LQNj receiving the request reference, the C1 container containing the LQNj and its neighbors; in case of a successful request for the network address (s) corresponding to the identifier, direct return of the query results; in case of unsuccessful request for the network address corresponding to the identifier, return a negative result of the request;

step 4), for any condition satisfying 1≤i≤I-1, check if Ti≤Ts <Ti + 1: if Ti≤Ts <Ti + 1 is satisfied, go to the next step if Ti≤Ts < Ti + 1 is not satisfied, go directly to step 7);

step 5) when Ti≤Ts <Ti + 1, forwarding the request to the request node of the Ci level container containing LQNj and designating the container as Cik, and performing a preliminary query in Cik and its neighbor list {Cim}; in case of a successful request for the network address (s) corresponding to the identifier, go to the next stage; in case of unsuccessful request for the network address corresponding to the identifier, return a negative result of the request;

step 6) requesting Cik and its neighbor list {Cim}; in the case of a successful request for the network address (network addresses) corresponding to the identifier, direct return of the query results, in the case of an unsuccessful request for the network address corresponding to the identifier, return a negative result of the request;

step 7), executing the preliminary request in the container of the CI level containing the LQNj; in case of a successful request for the network address (s) corresponding to the identifier, go to the next stage; in case of unsuccessful request for the network address corresponding to the identifier, go directly to step 9);

step 8), requesting in the container of the CI level containing the LQNj; in case of a successful request for the network address (s) corresponding to the identifier, direct return of the query results; in case of unsuccessful request for the network address corresponding to the identifier, go to the next stage;

step 9) requesting the neighbor list {CIm} of the CI layer container containing the LQNj through inter-domain exchange; in case of successful request of the network address (s) corresponding to the identifier in a certain container of the CI level, designating the container as CIp and proceeding to the next stage; in case of unsuccessful request for the network address corresponding to the identifier, return a negative result of the request; and

Step 10), forwarding the CIp request and requesting the CIp; in case of a successful request for the network address (s) corresponding to the identifier, direct return of the query results; in case of unsuccessful request for the network address corresponding to the identifier, return a negative result of the request;

preferably in step 3) the query is executed in the LQNj receiving the request reference, the C1 container containing the LQNj, and the local hash table (HT) in the neighbors;

preferably in step 5) the query is performed on a Bloom filter (BF) in Cik and its neighbor list {Cim};

preferably in step 6) the query is performed on a distributed hash table (DHT) in Cik and its neighbor list {Cim};

preferably in step 7) the preliminary request is performed in a Bloom filter (BF) in a container of the CI layer containing LQNj;

preferably in step 8) the query is performed on a distributed hash table (DHT) in a CI-level container containing LQNj;

preferably in step 9) the query is performed in a Bloom filter (BF) in the neighbor list {CIm} of the CI layer container containing LQNj; and

preferably the query is performed on a distributed hash table (DHT) in the CIp.

In the above technical solution, regarding the flow of nearest requests with the requirements of a given low latency, in order to save maintenance costs, the list of neighbors {C1m} C1k can be reduced to a C1 level container with no neighbors, and the specific flow of requests includes the following:

step 1) when Ti <Ts, receiving by a certain local node a request (LQNj) a request request for a given low time delay requirement directed to a specific subject unique identifier (ID), where Ti is the current actual request time delay index, and Ts is the upper limit of the time delay;

step 2) when i = 1, judging whether Ts <T1 is satisfied: if Ts <T1, go to the next step; if Ts is greater than or equal to T1, go directly to step 4);

step 3), when Ts <T1 and i = 1, requesting the LQNj receiving the request access, the C1 container containing the LQNj, and the neighboring elements of the container; in case of a successful request for the network address (s) corresponding to the identifier, direct return of the query results; in case of unsuccessful request for the network address corresponding to the identifier, return a negative result of the request;

step 4), for any condition satisfying 1≤i≤I-1, check if Ti≤Ts <Ti + 1: if Ti≤Ts <Ti + 1 is satisfied, go to the next step if Ti≤Ts < Ti + 1 is not satisfied, go directly to step 7);

step 5) when Ti≤Ts <Ti + 1, forwarding the request to the request node of the Ci level container containing LQNj and designating the container as Cik, and performing a preliminary query in Cik and its neighbor list {Cim}; in case of a successful request for the network address (s) corresponding to the identifier, go to the next stage; in case of unsuccessful request for the network address corresponding to the identifier, return a negative result of the request;

step 6) requesting Cik and its neighbor list {Cim}; in the case of a successful request for the network address (network addresses) corresponding to the identifier, direct return of the query results, in the case of an unsuccessful request for the network address corresponding to the identifier, return a negative result of the request;

step 7), executing the preliminary request in the container of the CI level containing the LQNj; in case of a successful request for the network address (s) corresponding to the identifier, go to the next stage; in case of unsuccessful request for the network address corresponding to the identifier, go directly to step 9);

step 8), requesting in the container of the CI level containing the LQNj; in case of a successful request for the network address (s) corresponding to the identifier, direct return of the query results; in case of unsuccessful request for the network address corresponding to the identifier, go to the next stage;

preferably in step 5) the query is performed on a Bloom filter (BF) in Cik and its neighbor list {Cim};

preferably in step 6) the query is performed on a distributed hash table (DHT) in Cik and its neighbor list {Cim};

preferably in step 7) the preliminary request is performed in a Bloom filter (BF) in a container of the CI layer containing LQNj;

preferably in step 8) the query is performed on a distributed hash table (DHT) in a CI layer container containing LQNj.

In conclusion, it should be understood that the above embodiments are used solely to explain the technical solutions of the present invention and not to limit the present invention. Although the present invention has been described in detail with reference to the embodiments, it will be understood by those skilled in the art that any modifications or equivalent substitutions made to the technical solutions of the present invention are within the spirit and scope of the technical solutions of the present invention and are included in the scope of the claims of the present invention.

Claims (37)

1. A query enhancement system for creating a distributed resource group based on a time delay, comprising: network nodes logically separated based on a set of time delay indices {Ti} to obtain a container group consisting of a plurality of containers with a nested relationship, each container containing a control node used to organize nodes, maintain neighborhood and serve requests in a container; wherein each time delay index Ti corresponds to a layer of the Ci level container without crossing and with full coverage, and the Ci level containers have a nested relationship with each other, that is, a set of Ci level containers make up a Ci + 1 level container, while Ti <Ti + 1, 1 i I-1, where I is the number of nested container layers and Ti is the actual time delay index of the request; wherein the control topology of the request enhancement system for creating the allocated resource group based on the time delay is a tree structure, and the root node is a CI-level container control node; the local request node, which is accessed by any request call, is denoted as LQNj and forms a portion of the resource group to be allocated together with the Ci level container containing the local request node (LQNj) and the neighboring elements of the container to satisfy the requirements of the request, which is that the time delay index {Ti} should be less than any predetermined upper limit of the time delay Ts. 2. The system of claim. 1, characterized in that the request requirement that the time delay index {Ti} must be less than any specified upper limit of the time delay Ts, in particular, provides the following: a) when Ts <T1, i = 1, a request in the LQNj receiving the request reference, the C1 container containing the LQNj, and the neighboring elements of the container; b) when Ti≤Ts <Ti + 1, requesting in the container of the Ci level containing LQNj, and neighboring elements of the container; and c) when Ts≥TI and i = I, request in the CI container containing LQNj. 3. A request enhancement method based on a request enhancement system for creating a distributed resource group based on a time delay according to claim 1 or 2, including: subjecting network nodes to logical separation without intersection and with full coverage on each layer to obtain a group of containers consisting of a plurality containers, and the plurality of containers have a nested relationship, and, accordingly, the execution of the flow of requests without the requirements of a given low time delay and the flow of nearby requests with the requirements of a given low time delay; wherein the request flow without the requirement of a given low latency applies request technologies such as direct matching, aggregation request, Skyline request, and Top-k request to implement the request to obtain the network address (s) corresponding to the identifier; With respect to the flow of requests with the requirements of a predetermined low time delay, a distributed closest request is applied taking into account the positional relationship from near to far, as a result of which the actual request time delay index Ti is less than the requirement of a certain upper limit of the time delay Ts. 4. The method according to claim 3, characterized in that, with respect to the nearest request, the requirement that the actual index of the time delay of the request Ti is less than a certain upper limit of the time delay Ts, in particular, provides the following: step 1) when Ti <Ts, receiving by a certain local node a request (LQNj) a request request with a predetermined low time delay, directed to a specific unique identifier (ID) of the subject, where Ti is the actual index of the time delay of the request, and Ts is the upper limit of the time delay; step 2), when i = 1, evaluating whether Ts <T1 is satisfied, and if Ts <T1, go to the next step; if Ts is greater than or equal to T1, go directly to step 4); step 3), when Ts <T1 and i = 1, requesting the LQNj receiving the request access, the C1 container containing the LQNj, and the neighboring elements of the container; in case of a successful request for the network address (s) corresponding to the identifier, direct return of the query results; in case of unsuccessful request for the network address corresponding to the identifier, return a negative result of the request; step 4), for any i satisfying 1≤i≤I-1, checking if Ti≤Ts <Ti + 1: if Ti≤Ts <Ti + 1 is satisfied, go to the next step if Ti≤Ts < Ti + 1 is not satisfied, go directly to step 7); step 5) when Ti≤Ts <Ti + 1, forwarding the request to the request node of the Ci level container containing LQNj and designating the container as Cik, and performing a preliminary query in Cik and its neighbor list {Cim}; in case of a successful request for the network address (s) corresponding to the identifier, go to the next stage; in case of unsuccessful request for the network address corresponding to the identifier, return a negative result of the request; step 6) requesting Cik and its neighbor list {Cim}; in the case of a successful request for the network address (network addresses) corresponding to the identifier, direct return of the query results, in the case of an unsuccessful request for the network address corresponding to the identifier, return a negative result of the request; step 7), executing the preliminary request in the container of the CI level containing the LQNj; in case of a successful request for the network address (s) corresponding to the identifier, go to the next stage; in case of unsuccessful request for the network address corresponding to the identifier, go directly to step 9); step 8), requesting in the container of the CI level containing the LQNj; in case of a successful request for the network address (s) corresponding to the identifier, direct return of the query results; in case of unsuccessful request for the network address corresponding to the identifier, go to the next stage; step 9) requesting the neighbor list {CIm} of the CI layer container containing the LQNj through inter-domain exchange; in case of successful request of the network address (s) corresponding to the identifier in a certain container of the CI level, designating the container as CIp and proceeding to the next stage; in case of unsuccessful request for the network address corresponding to the identifier, return a negative result of the request; and Step 10), forwarding the CIp request and requesting the CIp; in case of a successful request for the network address (s) corresponding to the identifier, direct return of the query results; in case of unsuccessful request for the network address corresponding to the identifier, return a negative result of the request. 5. The method according to claim 3, characterized in that in step 3) the request is performed in the LQNj receiving the request access, the C1 container containing the LQNj, and the local hash table (HT) in the neighboring elements. 6. The method according to claim 3, characterized in that in step 5) the query is performed in a Bloom filter (BF) in Cik and its neighbor list {Cim}. 7. The method according to claim 3, characterized in that in step 6) the query is performed on a distributed hash table (DHT) in Cik and its neighbor list {Cim}. 8. The method according to claim 3, characterized in that in step 7) the preliminary request is performed in a Bloom filter (BF) in a container of the CI level containing LQNj. 9. The method according to claim 3, characterized in that in step 8) the query is performed in a distributed hash table (DHT) in a CI-level container containing LQNj. 10. The method according to claim 3, characterized in that in step 9) the request is performed in a Bloom filter (BF) in the neighbor list {CIm} of the CI level container containing LQNj. 11. The method according to claim 3, characterized in that in step 10) the query is performed in a distributed hash table (DHT) in the CIp. 12. The method according to claim 3, characterized in that, with respect to the flow of closest requests with the requirements of a given low time delay, the list of neighbors {C1m} C1k can be reduced to a C1 level container without neighbors, and the specific flow of requests includes the following: step 1) when Ti <Ts, receiving by a certain local node a request (LQNj) a request request with a predetermined low time delay, directed to a specific unique identifier (ID) of the subject, where Ti is the actual index of the time delay of the request, and Ts is the upper limit of the time delay; step 2), when i = 1, evaluating whether Ts <T1 is satisfied, and if Ts <T1, go to the next step; if Ts is greater than or equal to T1, go directly to step 4); step 3), when Ts <T1 and i = 1, requesting the LQNj receiving the request access, the C1 container containing the LQNj, and the neighboring elements of the container; in case of a successful request for the network address (s) corresponding to the identifier, direct return of the query results; in case of unsuccessful request for the network address corresponding to the identifier, return a negative result of the request; step 4), for any i satisfying 1≤i≤I-1, checking if Ti≤Ts <Ti + 1: if Ti≤Ts <Ti + 1 is satisfied, go to the next step if Ti≤Ts < Ti + 1 is not satisfied, go directly to step 7); step 5) when Ti≤Ts <Ti + 1, forwarding the request to the request node of the Ci level container, which contains LQNj and denoted as Cik, and performing a preliminary request in Cik and its neighbor list {Cim}; in case of a successful request for the network address (s) corresponding to the identifier, go to the next stage; in case of unsuccessful request for the network address corresponding to the identifier, return a negative result of the request; preferably the query is executed in a Bloom filter (BF) in Cik and its neighbor list {Cim}; step 6) requesting Cik and its neighbor list {Cim}; in the case of a successful request for the network address (network addresses) corresponding to the identifier, direct return of the query results, in the case of an unsuccessful request for the network address corresponding to the identifier, return a negative result of the request; preferably the query is executed on a distributed hash table (DHT) in Cik and its neighbor list {Cim}; step 7), executing the preliminary request in the container of the CI level containing the LQNj; in case of a successful request for the network address (s) corresponding to the identifier, go to the next stage; in case of unsuccessful request for the network address corresponding to the identifier, go directly to step 9); preferably in step 7) the preliminary request is performed in a Bloom filter (BF) in a container of the CI layer containing LQNj; and step 8), requesting in the container of the CI level containing the LQNj; in case of a successful request for the network address (s) corresponding to the identifier, direct return of the query results; in case of unsuccessful request for the network address corresponding to the identifier, go to the next stage; preferably in step 8) the query is performed on a distributed hash table (DHT) in a CI layer container containing LQNj.

Images